KR20170047315A - Improved network utilization in policy-based networks - Google Patents

Abstract

In one embodiment, the method includes receiving a data packet at a routing engine of a node of the network. In order to transmit a data packet from the node to the destination of the data packet, a route is selected from the transmission table of the node. The transmission table includes the root property, which includes the root cost associated with two or more routes from the node to the destination. The hardware computing device analyzes the selected route and determines, based on the real-time traffic information, whether the selected route is suitable for delivering the data packet. If it is determined that the selected route is unsuitable for delivering the data packet, the data packet is returned to the routing engine. If the previous selected route is unsuitable for delivering the data packet, a replacement route for the data packet instead of the previously selected route is selected from the transmission table.

Description

[0001] IMPROVED NETWORK UTILIZATION IN POLICY-BASED NETWORKS [0002]

This disclosure relates to networking, and more particularly, to improving network utilization in policy-based networks where the network may be dynamic.

Policy routing networks with multiple paths between source and destination are typically not optimized to use such multiple paths, and artificially reduce the throughput of the network, especially in situations where topology and link quality vary over time. If the link is saturated for a given Quality of Service (QoS) level or a differentiated service code point (DSCP) value, additional traffic is dropped, even if a suitable alternate path is available. At the drop of data, important information can be lost or time-sensitive information can be over-delayed. This is especially important in tactical networks where loss or delay can have serious consequences.

Conventional network managers have rules for policy-based management that determine which routes should be taken based on QoS level or DSCP value, but if such a route gets stuck, the data is typically dropped.

In one embodiment, the method includes receiving a data packet at a routing engine of a node of the network. In order to transmit a data packet from the node to the destination of the data packet, a route is selected from the transmission table of the node. The transmission table includes the root property, which includes the root cost associated with two or more routes from the node to the destination. The computer hardware computing device analyzes the selected route to determine, based on the real-time network traffic, whether the selected route is suitable for delivering the data packet. If it is determined that the selected route is unsuitable for delivering the data packet, the data packet is returned to the node's routing engine. If it is determined that the previous selected route is unsuitable for delivering the data packet, a replacement route for the data packet is selected from the transmission table instead of the previously selected route.

In another embodiment, the system comprises a node of a network, the node comprising a routing engine and a traffic shaper associated with the outbound interface of the routing engine. The routing engine receiving the data packet; From the transmission table of the node, a route for transmitting the data packet from the node to the destination of the data packet. The transmission table includes the root property, which includes the root cost associated with two or more routes from the node to the destination. The traffic shaper is configured by the hardware computing device to analyze the selected route and determine, based on the real-time traffic information, whether the selected route is suitable for delivering the data packet. The traffic shaper is further configured to return the data packet to the node's routing engine if the selected route is determined to be unsuitable for delivering the data packet. The routing engine is further configured to select a substitute route for the data packet from the transmission table instead of the previously selected route if the previously selected route is determined to be unsuitable for delivering the data packet.

In yet another embodiment, the computer program product comprises a computer readable storage medium embodying computer readable program code. The computer readable program code is executable by the processor to perform the method. The method includes receiving a data packet from a routing engine of a node of the network. In order to transmit a data packet from the node to the destination of the data packet, a route is selected from the transmission table of the node. The transmission table includes the root property, which includes the root cost associated with two or more routes from the node to the destination. The computer hardware computing device analyzes the selected route to determine, based on the real-time network traffic, whether the selected route is suitable for delivering the data packet. If it is determined that the selected route is unsuitable for delivering the data packet, the data packet is returned to the node's routing engine. If it is determined that the previous selected route is unsuitable for delivering the data packet, a replacement route for the data packet is selected from the transmission table instead of the previously selected route.

Additional features and advantages are realized through the teachings of the present disclosure. Other embodiments and aspects of the disclosure are described in detail herein and are considered a part of the claims. For a better understanding of the present disclosure and its advantages and features, reference is made to the description and drawings.

BRIEF DESCRIPTION OF THE DRAWINGS For a more complete understanding of the present disclosure, reference is now made to the following brief description taken in conjunction with the accompanying drawings and detailed description, wherein like reference numerals designate like elements.
1 is a block diagram of a routing system node in accordance with some embodiments of the present disclosure.
2 is a flow diagram of a method for routing data packets in a network in accordance with some embodiments of the present disclosure.
3 is a block diagram of a computer system for implementing some or all aspects of a routing system in accordance with some embodiments of the present disclosure.

According to some embodiments of the present routing system, data packets may be rerouted instead of being dropped due to congestion, i.e., link saturation or other traffic shaping problems. In general, the routing system can identify that the selected "best" route is experiencing link saturation or other problems, dynamically identify one or more possible alternate routes for data, and utilize at least one of these alternate routes. Thus, instead of dropping packets, the routing system can dynamically use alternative routes, perhaps at different but compatible QoS levels, towards the destination of the data packet.

The routing system may use other identified valid routes to select from them based on, for example, the desired destination address, QoS and DSCP marking. If such an alternate route exists, the routing system may transmit the packet along such alternate route instead of the route that caused the drop of the packet. Various embodiments of the routing system may eliminate the need to drop packets in the case of congestion or traffic shaping problems, improve the utilization of the entire network, and thereby reduce the need for retransmissions. Since embodiments of the present routing system can dynamically select routes, such embodiments can thus more efficiently utilize the dynamic network.

1 is a block diagram of at least a portion of a node 110 of a network, which includes aspects of a routing system 100 in accordance with some embodiments of the present disclosure. The node 110 may be a routing node for a network managed by the routing system 100. It will be appreciated that node 110 may include other components than those shown. The network may include one or more of such nodes 110 that together can route data packets over the network. As shown, the node 110 may include a routing engine 120 and one or more network interfaces 130. Each network interface 130 may include a traffic shaper 140 connected to one or more downstream entities 160 (e.g., a weighed fair queue). Although a plurality of network interfaces 130 are shown in FIG. 1, only two network interfaces 130 may be included in a single node 110. Each downstream entity 160 may include an interface to a corresponding physical link connecting the current node 110 to the neighboring node 110. [

A data packet may be received at a node 110 from a neighboring node via one of the network interfaces 130 of the node, in which case the one network interface acts as an entrance interface. In contrast, when a data packet is transmitted from a node 110 via a particular network interface 130, the network interface 130 acts as an exit interface.

Routing engine 120 may make routing decisions for each data packet received at node 110. [ More specifically, the routing engine 120 may determine, through traditional policy decisions, whether the route deemed best fit for the data packet is unsuitable for processing the data packet due to congestion or other reasons. In such a case, the routing engine 120 may select the best alternate route for the data packet.

According to conventional routing techniques, the routing engine of the node maintains a transmission table indicating the best route for each destination that the routing engine knows. Such a best route can be maintained if the plurality of best routes to the destination have the same cost or if the cost difference is within a predefined threshold. Data stored in the transmission table is formed through communication with neighboring nodes, which are eventually communicating with its neighboring nodes, and so on. Thus, through communication between the various nodes between the first node and the destination, the first node determines the best route to the destination. Also, since each node knows its neighbor links (i.e., connections to neighbor nodes), the various nodes can communicate network topology changes with each other. If a topology change or other change to the network introduces a new best route, the first node will eventually know it through communication with the other node. In this case, the new best route will replace the previous best route in the routing table of the routing engine.

In conventional systems, along with the best route, the routing engine also maintains the cost of that route. Root cost calculations are generally policy dependent. For example, the cost of the route stored by the first node may be the number of hops (i.e., links between nodes) between the first node and the destination. According to the prior art, only the best route (i.e., the route with the lowest cost or the route with the lowest similar cost) is kept in the transmission table for each destination maintained in the transmission table. All other routes are discarded and forgotten. Thus, according to the prior art, when a data packet is received for delivery to a particular destination, the routing engine selects the currently known best route.

In some embodiments of the routing system 100 according to the present disclosure, as in the prior art, the nodes 110 may communicate with each other, and each node may maintain a transmission table 125. However, the forwarding table 125 may maintain one or more routes for each known destination. When a new route is identified, the route may be added to the forwarding table 125 with the cost of that route, but existing known routes need not be removed from the forwarding table 125. According to some embodiments, when first selecting the best route, the routing engine 120 may select the current best route (e.g., the lowest cost route) among the available routes for the destination, as stored in the forwarding table .

Based on the selected route, the routing engine 120 may identify the corresponding network interface 130. In some embodiments, a separate network interface 130 may be used for each link from the current node 110, so that route selection can uniquely determine the corresponding network interface associated with the first link of the selected route have.

Each network interface 130 may include a traffic shaper 140 and an associated downstream entity 160. Traffic shaper 140 may include one or more traffic queues. Traffic shaper 140 may place data packets in a particular queue based on a user configurable policy. By way of example, and not limitation, traffic shaper 140 may use a token bucket as a traffic meter to maintain a data packet output rate, i. The various data packets on the queue may eventually be dequeued and, in some cases, sent to the downstream entity 160.

Before a packet is sent to the downstream entity 160, the traffic shaper 140 may determine from the network interface 130 that the selected route starting at the succeeding link is suitable for delivering the data packet. If the selected route is deemed appropriate, the traffic shaper 140 may forward the packet to the downstream entity 160.

Even when the selected route is the traditional "best" route, there may be a situation where the selected route is not suitable for delivering a particular data packet. By way of example, and not limitation, a data packet may need to be dropped in the event of a profile (i.e., contract) out of compliance with a user configurable policy, or when the applicable queue is full. According to the prior art, in this situation, the data packet will be dropped or discarded by the traffic shaper 140 according to the user configurable policy.

The determination of the suitability of the selected route for delivering the data packet may be determined by existing policies that may be set by the network administrator and enforced by the various nodes 110 of the network. By way of example and not of limitation, the route may be due to congestion when its utilization exceeds a predetermined threshold, such as a threshold of 80% loading on any one link of the route; Due to having insufficient bandwidth to transmit packets; (I.e., a delay exceeding a time frame of a predetermined threshold) between the transmission of a previous data packet to the corresponding physical interface of the downstream entity 160 and the transmission of such data packet over the adjacent link It can be regarded as unsuitable due to its existence. As another example, the route may be deemed unsuitable if the jitter of the route exceeds a predetermined threshold.

According to the prior art, the traffic shaper examines and analyzes the selected route based on the current network policy to determine whether the selected route is currently suitable for delivering the data packet (e.g., whether the data packet is in the profile) . If the selected route is deemed appropriate for the data packet, the traffic shaper may forward the data packet to the physical interface of the downstream entity 160. The physical interface may then transmit the data packet along a neighbor link corresponding to the selected route. If the selected route is not suitable, according to the prior art, the data packet will typically be queued, reclassified or dropped.

Some embodiments of the present disclosure are based on the prior art. According to some embodiments, the traffic shaper 140 does not need to drop the data packet due to non-compliance of the selected route. Rather, in such a case, the traffic shaper 140 may return the data packet to the routing engine 120. The routing engine 120 may then determine the best alternative route for sending the data packet to its destination. To this end, the routing engine 120 may identify one or more alternate routes for data packets. These alternative routes may have already been stored in the transmission table 125 as described above. In some embodiments, the identified alternate route may include all previously discovered routes from the current node 110 to the destination, since such a route did not have to be dropped at the time of identifying the new best route.

According to some embodiments, the routing engine 120 may maintain a plurality of alternative routes to each known destination in its transmission table 125. [ The routing engine 120 may also maintain various route data for alternate routes, the data may include respective route characteristics, and may be generated and maintained through communication between the various nodes of the network as described above. Route data may include the root cost of various alternative routes that may be calculated based on various factors such as, for example, QoS, bandwidth, latency, hop count and jitter.

After the previously selected route is deemed unsuitable for the data packet and such data packet is returned to the routing engine 120, the routing engine 120 may use the route data to select the best alternative route. The decision as to which route to choose as the best alternate route can be made through the use of various selection algorithms that can take into account the various traffic characteristics of the alternate route. As an example and not by way of limitation, the selection algorithm used may be a QoS aware algorithm and may consider a combination of at least one of QoS, DSCP marking, bandwidth, latency, hop count and jitter that contribute to the root cost and can be obtained from the root data have. In some embodiments, the selection algorithm may also consider an application in which a data packet is being transmitted. For example, a VoIP application will likely require a lower jitter than can be accommodated for web browsing. Thus, for VoIP packets, the best alternative route may be required to be below the jitter threshold. In another example, the selection algorithm may simply select the route with the highest bandwidth, or may use a round robin approach to assign the data packet to various alternate routes to the destination. It will be appreciated that various selection algorithms may be used to select the best alternate route among the available alternate routes in the forwarding table 125.

In some instances, choosing the best alternate route may be against, or at least mitigate, existing network policies. For example, a network policy may require that a data packet for a given application be transmitted along a route having at least a predetermined QoS or other desired characteristics. However, such a request may be harmful rather than beneficial when a legitimate packet is dropped due to the incompatibility of the first best route selected. According to some embodiments, such a data packet may instead be transmitted along a route with slightly lower QoS, which may yield a better result than dropping the data packet. Therefore, choosing the best alternate route can lead to better results than dropping the data packet. Instead of doing this when the congestion traditionally requires dropping of queued data, the routing system 100 may adapt the data packet and transmit it by another different route.

In some embodiments, the routing engine 120 may maintain, for example, the metadata stored in the data packet itself or in the routing engine 120, and the metadata may indicate which network interface 130 Indicates if it has been attempted. Before sending the data packet to the network interface 130 of the selected route, the routing engine 120 examines the metadata associated with the data packet to determine that the corresponding network interface 130 has not previously been attempted for the data packet Can be confirmed. If the network interface 130 for the selected route is already listed in such metadata, the routing engine 120 may select another best alternative route for the data packet, except for the route previously selected and determined to have already been attempted have. Also, the data packet would have been received at the node via one of the network interfaces 130, in which case the one network interface behaved as the ingress interface. To prevent route looping, in some embodiments, the routing engine 120 may avoid selecting the ingress interface as the originating network interface 130 for the data packet. In some embodiments, when transmitting a data packet to the network interface 130 for the selected route, the routing engine 120 may modify the associated metadata of the data packet to indicate that the network interface 130 has been attempted for the data packet .

If the selected route is considered appropriate for the data packet (which may be the best selected route that was initially selected or the best alternative route selected after return to the routing engine 120), the traffic shaper 140 sends the data packet to the downstream entity 160 ). The physical interface of the downstream entity 160 may then transmit data packets along a neighbor link corresponding to the selected route. However, if the selected route is deemed to be inadequate, the traffic shaper 140 sends the associated metadata of the data packet 130 to indicate that this network interface 130 has already been attempted (unless the routing engine 120 has already done this) And then return the data packet to the routing engine 120. [ The routing engine 120 may then select a new best alternative route for the data packet, as described above.

Alternatively, in some embodiments, when the selected route is not suitable, the traffic shaper 140 may drop the data packet if the traffic shaper 140 determines that the termination condition is met. By way of example, and not limitation, traffic shaper 140 may determine that a data packet has been returned to routing engine 120 for re-routing in a previous attempt or a predetermined number of prior attempts based on the associated metadata of the data packet The traffic shaper 140 may drop the data packet instead of returning it to the routing engine 120. [

2 is a flow diagram of a method 200 of routing data packets over a network in accordance with some embodiments of the present disclosure. As shown, at block 210, a data packet may be received at node 110. [ At block 220, a route may be selected for the data packet and a route is selected from the transmission table 125. Once the route is determined, the data packet is transmitted to the network interface 130 corresponding to the selected route. At decision block 230, the network interface 130 of the selected route may determine whether it is appropriate for the data packet. If the selected route is deemed appropriate, then at block 240 the data packet is forwarded to the downstream entity 160.

If the route selected at decision block 230 is deemed unsuitable for the data packet, decision block 250 determines if a replacement route is not available or a predetermined end condition is met. If a replacement route is not available at decision block 250, or if a predetermined end condition is met, the data packet is dropped at block 280. Otherwise, the data packet is returned to the routing engine 120. At block 270, a replacement route may be selected from the available alternate routes in the transmission table 125. The method 200 then returns to decision block 230 to determine if the network interface 130 of the selected alternate route is suitable for the data packet. Blocks 230 through 270 may be repeated until a suitable alternate route is found or until a data packet is dropped.

It will be appreciated that the method 200 is provided for illustrative purposes only. The method 200 may be modified based on an implementation, or other methods may be used in accordance with other embodiments of the present disclosure.

Thus, some embodiments of the present routing system 100 enable better utilization of the bandwidth of the network, since traffic to the overloaded link can be offloaded to a link that is not fully utilized. As a result, the routing system 100 may reduce the need to drop data compared to conventional routing techniques. In addition, the routing system 100 may respond to topology changes before the routing protocol converges. For example, as the primary link degrades before the topology change, the alternate link can automatically begin to deliver more traffic.

Some embodiments of the routing system 100 may be implemented in whole or in part by a computer system or computer hardware. By way of example, and not limitation, a routing system may be implemented by a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or custom logic. 3 illustrates a block diagram of a computer system 300 for use in implementing routing system 100 or method 200 in accordance with some embodiments. The routing system 100 and method 200 described herein may be implemented in hardware, software (e.g., firmware), or a combination thereof. For example, one or more nodes 110 of routing system 100 may be implemented in computer system 300 as shown in FIG.

In the exemplary embodiment, the described methods may be implemented at least partially in hardware and may be part of a microprocessor of a special or general purpose computer system 300, such as a personal computer, workstation, minicomputer, or mainframe computer.

3, the computer system 300 includes a processor 305, a memory 310 coupled to the memory controller 315, and a local I / O controller 335 for communicating < RTI ID = One or more input devices 345 and / or output devices 340, such as peripheral devices, possibly coupled. These devices 340 and 345 may include, for example, a printer, a scanner, a microphone, and the like. The conventional keyboard 350 and the mouse 355 may be coupled to the I / O controller 335. For example, I / O controller 335 may be one or more buses or other wired or wireless connections as is known in the art. I / O controller 335 may have additional components such as a controller, a buffer (cache), a driver, a repeater and a receiver to enable communication, which are omitted for simplicity.

The I / O devices 340 and 345 may be devices that communicate both input and output, such as disk and tape storage, network interface cards (NICs) (for accessing other files, devices, systems or networks) / Demodulator, radio frequency (RF) or other transceiver, telephone interface, bridge, router, and the like.

Processor 305 is a hardware device for executing hardware instructions or software, particularly those stored in memory 310. Processor 305 may be any of a variety of processors associated with a custom or commercial processor, a central processing unit (CPU), computer system 300, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macro processor, Lt; / RTI > The processor 305 may be implemented with a processor, such as an instruction cache for accelerating executable instruction fetch, a data cache for accelerating data fetch and storage, and a translation lookaside buffer 302 for use in accelerating virtual / physical address translations for both executable instructions and data. And a cache 370 that may include, but is not limited to, a TLB. The cache 370 may be configured with a hierarchical structure of more cache levels (L1, L2, etc.).

The memory 310 may include volatile memory elements (e.g., random access memory (RAM), such as DRAM, SRAM, SDRAM, etc.) and non-volatile memory elements (e.g., ROM, erasable and programmable read- ), Electrically erasable and programmable read only memory (EEPROM), programmable read only memory (PROM), tape, compact disk read only memory (CD ROM), disk, diskette, cartridge, cassette, As shown in FIG. The memory 310 may also include electronic, magnetic, optical or other types of storage media. It is noted that memory 310 may have a distributed architecture in which various components may be located apart from one another but accessed by processor 305. [

The instructions in memory 310 may include one or more individual programs, each of which includes an ordered list of executable instructions for implementing the logical function. In the example of FIG. 3, the instructions in memory 310 include an appropriate operating system (OS) 311. Operating system 311 is essentially capable of controlling the execution of other computer programs and provides scheduling, input / output control, file and data management, memory management, and communication control and related services.

Additional data including, for example, instructions for processor 305 or other searchable information may be stored in storage 320, which may be a hard disk drive or a storage device such as a solid state drive. The stored instructions in memory 310 or storage 320 may include instructions that enable a processor to execute one or more aspects of routing system 100 and method 200 of the present disclosure.

The computer system 300 may further include a display controller 325 coupled to the display 330. In an exemplary embodiment, the computer system 300 may further comprise a network interface 360 for coupling to the network 365. [ Network 365 may be an IP-based network for communicating between computer system 300 and any external server, client, etc., over a broadband connection. The network 365 transmits and receives data between the computer system 300 and the external system. In an exemplary embodiment, network 365 may be a managed IP network managed by a service provider. The network 365 may be implemented in a wireless manner using wireless protocols and technologies such as, for example, Wi-Fi, WiMAX, and the like. The network 365 may be a packet-switched network, such as a local area network, a wide area network, an urban area network, the Internet or other similar types of network environments. The network 365 may be a fixed wireless network, a wireless local area network (LAN), a wireless wide area network (WAN), a personal area network (PAN), a virtual private network (VPN), an intranet, And the like.

The routing system 100 and method 200 in accordance with the present disclosure may be implemented in whole or in part in a computer program product or in a computer system 300 such as that shown in FIG.

The corresponding structures, materials, operations, and equivalents of all means or step-plus functional elements in the claims below include any structure, material, or action for performing a function in combination with other claimed elements, as specifically claimed It is intended to do. Although the description herein is provided for illustrative purposes, it is not intended to be exhaustive or to limit the embodiments specifically described. Many modifications and variations will become apparent to those skilled in the art without departing from the scope and spirit of the present disclosure. The embodiments are chosen and described in order to best explain the principles and practical applications of various embodiments and to enable others of ordinary skill in the art to understand various embodiments having various modifications as are suited to the particular use contemplated And described.

Although some embodiments have been described, it will be appreciated by those skilled in the art that various improvements and enhancements may be made within the scope of the claims which follow, both now and in the future. Such claims should be construed as maintaining adequate protection to the present disclosure.

Claims (20)

As a method,
Receiving a data packet at a routing engine of a node of the network;
Selecting a route from the node's forwarding table to transmit the data packet from the node to a destination of the data packet, the transmission table comprising at least two Comprising route characteristics, including route costs, associated with the route;
Analyzing the selected route by the hardware computing device to determine if the selected route is suitable for delivering the data packet based on real-time traffic information;
Returning the data packet to the routing engine of the node if the selected route is determined to be unsuitable for delivering the data packet; And
Selecting a replacement route for the data packet instead of the previous selected route from the transmission table if a previous selected route is determined to be unsuitable for delivering the data packet;
/ RTI > The method according to claim 1,
Analyzing the selected route to determine whether the selected route is suitable for conveying the data packet until the selected alternate route is deemed suitable for conveying the data packet, Repeating the step of selecting a replacement route for the data packet; And
Transmitting the data packet along the selected alternate route after the selected alternate route is deemed suitable for carrying the data packet
≪ / RTI > The method according to claim 1,
Analyzing the selected route to determine whether the selected route is suitable for delivering the data packet until a termination condition is met and selecting an alternate route for the data packet instead of the previous selected route Repeating; And
Dropping said data packet after said termination condition is met
≪ / RTI > 2. The method of claim 1, further comprising maintaining metadata associated with the data packet, wherein the metadata includes information about which routes from the node to the destination are analyzed for suitability to deliver the data packet Lt; / RTI > 2. The method of claim 1, wherein selecting the alternate route for the data packet comprises:
Identifying, in the transfer table, two or more alternate routes from the node to the destination;
Comparing the root characteristics of the at least two alternative routes; And
Selecting the selected alternate route from the at least two alternate routes based at least in part on the route characteristics
/ RTI > 6. The method of claim 5, wherein comparing the route characteristics of the two or more alternate routes comprises comparing service quality along the two or more alternate routes. 6. The method of claim 5, wherein comparing the root characteristics of the two or more alternate routes is performed based at least in part on an application in which the data packet is being transmitted. As a system,
Comprising a node of the network, the node
A routing engine configured to receive a data packet and select a route from the node's transport table to the destination of the data packet from the node, the transport table comprising two Comprising root properties, including root costs, associated with the above roots; And
A traffic shaper associated with the outbound interface of the routing engine,
, The traffic shaper
Analyze, by the hardware computing device, the selected route based on real-time traffic information, to determine whether the selected route is suitable for delivering the data packet;
And return the data packet to the routing engine of the node if the selected route is determined to be unsuitable for delivering the data packet;
Wherein the routing engine is further configured to select, from the transmission table, a replacement route for the data packet instead of the previous selected route if a previous selected route is determined to be unsuitable for delivering the data packet. 9. The method of claim 8, wherein the traffic shaper repeats the selected route to determine whether the selected route is suitable for delivering the data packet until the selected alternate route is deemed eligible to deliver the data packet. Wherein the routing engine is configured to iteratively select a replacement route for the data packet instead of the previous selected route;
Wherein the node further comprises a network interface configured to transmit the data packet along the selected alternate route after the selected alternate route is deemed suitable for carrying the data packet. 9. The method of claim 8, wherein until the termination condition is met, the traffic shaper is configured to iteratively analyze the selected route to determine whether the selected route is suitable for delivering the data packet, ≪ / RTI > alternatively selecting a substitute route for said data packet instead of a selected route of said data packet;
The traffic shaper is further configured to drop the data packet after the termination condition is satisfied. 9. The method of claim 8, wherein the routing engine is further configured to maintain metadata associated with the data packet, wherein the metadata indicates which routes from the node to the destination have been analyzed for conformance to deliver the data packet ≪ / RTI > 9. The system of claim 8, wherein the routing engine
Identifying, in the transfer table, two or more alternate routes from the node to the destination;
Compare the root characteristics of the two or more alternative routes;
And selecting the selected alternate route from the at least two alternate routes based at least in part on the route characteristics
And to select the selected alternate route for the data packet. 13. The system of claim 12, wherein comparing the route characteristics of the at least two alternative routes comprises comparing service quality along the at least two alternative routes. 13. The system of claim 12, wherein comparing the route characteristics of the two or more alternate routes is performed based at least in part on the application to which the data packet is being sent. A computer program product comprising a computer readable storage medium embodying computer readable program code, the computer readable program code being executable by a processor to perform a method,
Receiving a data packet at a node of the network;
Selecting a route from the node's transfer table to transfer the data packet from the node to a destination of the data packet, wherein the transfer table includes route costs associated with two or more routes from the node to the destination Containing root properties;
Analyzing the selected route based on real-time traffic information to determine if the selected route is suitable for delivering the data packet;
Returning the data packet to the routing engine of the node if the selected route is determined to be unsuitable for delivering the data packet; And
Selecting a replacement route for the data packet instead of the previous selected route from the transmission table if a previous selected route is determined to be unsuitable for delivering the data packet;
And a computer program product. 16. The method of claim 15,
Analyzing the selected route to determine whether the selected route is suitable for conveying the data packet until the selected alternate route is deemed suitable for conveying the data packet, Repeating the step of selecting a replacement route for the data packet; And
Transmitting the data packet along the selected alternate route after the selected alternate route is deemed suitable for carrying the data packet
The computer program product further comprising: 16. The method of claim 15,
Analyzing the selected route to determine whether the selected route is suitable for delivering the data packet until a termination condition is met and selecting an alternate route for the data packet instead of the previous selected route Repeating; And
Dropping the data packet after the termination condition is satisfied
The computer program product further comprising: 16. The method of claim 15, wherein the method further comprises maintaining metadata associated with the data packet, wherein the meta data includes information about which routes from the node to the destination are analyzed for suitability to deliver the data packet The computer program product. 16. The method of claim 15, wherein selecting the alternate route for the data packet comprises:
Identifying, in the transfer table, two or more alternate routes from the node to the destination;
Comparing the root characteristics of the at least two alternative routes; And
Selecting the selected alternate route from the at least two alternate routes based at least in part on the route characteristics
And a computer program product. 20. The computer program product of claim 19, wherein comparing the route characteristics of the two or more alternate routes comprises comparing service quality along the two or more alternate routes.

Images